DE102009007514B4 - Method and apparatus for monitoring a weld signature - Google Patents

Method and apparatus for monitoring a weld signature

Info

Publication number
DE102009007514B4
DE102009007514B4 DE102009007514A DE102009007514A DE102009007514B4 DE 102009007514 B4 DE102009007514 B4 DE 102009007514B4 DE 102009007514 A DE102009007514 A DE 102009007514A DE 102009007514 A DE102009007514 A DE 102009007514A DE 102009007514 B4 DE102009007514 B4 DE 102009007514B4
Authority
DE
Germany
Prior art keywords
weld
signature
welding
30a
neural network
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
DE102009007514A
Other languages
German (de)
Other versions
DE102009007514A1 (en
Inventor
Jay Hampton
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
GM Global Technology Operations LLC
Original Assignee
GM Global Technology Operations LLC
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority to US12/028,431 priority Critical
Priority to US12/028,431 priority patent/US20090200282A1/en
Application filed by GM Global Technology Operations LLC filed Critical GM Global Technology Operations LLC
Publication of DE102009007514A1 publication Critical patent/DE102009007514A1/en
Application granted granted Critical
Publication of DE102009007514B4 publication Critical patent/DE102009007514B4/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B23MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
    • B23KSOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
    • B23K9/00Arc welding or cutting
    • B23K9/095Monitoring or automatic control of welding parameters
    • B23K9/0953Monitoring or automatic control of welding parameters using computing means
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B23MACHINE TOOLS; METAL-WORKING NOT OTHERWISE PROVIDED FOR
    • B23KSOLDERING OR UNSOLDERING; WELDING; CLADDING OR PLATING BY SOLDERING OR WELDING; CUTTING BY APPLYING HEAT LOCALLY, e.g. FLAME CUTTING; WORKING BY LASER BEAM
    • B23K9/00Arc welding or cutting
    • B23K9/10Other electric circuits therefor; Protective circuits; Remote controls
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computer systems based on biological models
    • G06N3/02Computer systems based on biological models using neural network models

Abstract

One method monitors a weld signature of a welder by processing the signature through a neural network to recognize a pattern and classifying the weld signature in response to the pattern. The method determines whether the weld signature differs sufficiently from training weld signatures stored in a database and records the weld signature in the database if it sufficiently differentiates. The method tests a weld to determine values of different weld characteristics and then correlates the signature with the weld data to validate the database. A device monitors a weld signature during a weld process to predict weld quality, and includes a weld gun, power supply, and sensor to detect weld voltage, current, and wire feed rate (WFS). A neural network receives the welding process values and classifies the signature into different weld classifications, each corresponding to a predicted weld quality.

Description

  • TECHNICAL AREA
  • The invention relates generally to a method and apparatus for monitoring a weld signature during a welding process by classifying the weld signature using a neural network model or a neural processor.
  • BACKGROUND OF THE INVENTION
  • Welding systems are extensively used in various production processes to join or join different work surfaces. In particular, arc welding systems can be used to weld or fuse separate work surfaces firmly to a unified body via the controlled application of intense heat and an intermediate material to form a resultant weld. A solid metallurgical texture is formed when the intermediate material, which is rapidly melted in the presence of a high temperature arc during the arc welding process, eventually cools and solidifies. Ideally, the resulting weld has approximately the same overall strength and material properties as the original separate work surfaces.
  • In an arc welding process, the arc may be formed between the working surface and a consumable electrode such as a wire length that is controlled to be supplied to a welding gun as the welding gun moves along the weld, the arc being transmitted through an ionized arc protective gas column. The arc itself provides the high heat levels necessary to melt the consumable electrode or wire. Thus, the electrode conducts an electrical current between the tip of the welding tongs and the working surface, with the molten wire material serving as a filling material as it is fed to the weld.
  • The quality of a single weld can be determined using a destructive test, i. H. by physically breaking or cutting the weld under controlled conditions to precisely measure the strength and / or overall integrity of the weld. However, real-time monitoring of the welding process to accurately detect acceptable, "passed" or "good" welding may be a challenging process due to the large number of different welding system and environmental operating variables, which are interrelated and complex influence the resulting welding quality. Algorithmically comparing the various individual welding system variables to stored thresholds may also be sub-optimal due to the difficulty of accurately determining an isolated or individual contribution or effect of variance in a single variable value on the overall quality of a resulting weld.
  • The DE 41 12 985 C2 discloses a method and an apparatus for automatically guiding a welding head, which form a distance profile for each welding operation from measured current and voltage values, sampling the distance profile at measuring points with high temporal resolution and feeding all measuring points in parallel into a neural network in order to classify the distance profile to obtain.
  • In the DE 195 18 804 A1 discloses a method for monitoring a production process that generates process metrics from measured waveforms of the process and inputs them to a neural network to thereby obtain quality characteristics or classes.
  • The DE 199 57 163 C1 discloses a method and apparatus for quality control of the seam on laser-butt welded sheets or tapes that capture, latch and supply a variety of sensor data to a hierarchical neural network to obtain quality control evidence.
  • The object of the invention is to provide a method which allows a classification of a produced weld in a simple manner without algorithmic comparisons of welding process variables with threshold values.
  • This object is achieved by the method of claim 1.
  • SUMMARY OF THE INVENTION
  • According to the invention, a method for monitoring a weld signature during an arc welding process includes determining a plurality of different welding process variables that define the welding signature and including at least a welding voltage, a welding current, and a wire feeding speed (WFS). The method includes classifying the weld signature into one of a plurality of different weld classifications using a neural network. The neural network has a plurality of input nodes, each one of which corresponds to another welding process variable. The classification of the weld signature is characterized by the absence of a comparison of any of the various welding process variables with a corresponding threshold.
  • In a further aspect of the invention, the method compares the weld signature to a database of training weld signatures after the weld signature has been classified, determines whether the weld signature of each of the training weld signatures in the database is sufficiently different, and records the weld signature in the database Database when the neural network determines that the weld signature is sufficiently different from each of the training weld signatures.
  • In a further aspect of the invention, the method tests a weld after classification to determine a weld dataset containing the values of each of a plurality of different weld properties, and then correlates the weld signature with the weld dataset to validate the database.
  • The foregoing features and advantages and other features and advantages of the present invention will become more readily apparent from the following detailed description of the best modes for carrying out the invention when taken in conjunction with the accompanying drawings.
  • BRIEF DESCRIPTION OF THE DRAWINGS
  • 1 Fig. 12 is a schematic illustration of a welding apparatus and a controller used to monitor a welding signature according to the invention;
  • 2 FIG. 4 is a graphical representation of an exemplary acceptable or "passed" weld signature; FIG.
  • 3 FIG. 12 is a graphical illustration of an exemplary unacceptable or "failed" signature signature; FIG.
  • 4 FIG. 12 is a graphical representation of an artificial neuron model or neural network that is identical to the one in FIG 1 shown controller can be used; and
  • 5 FIG. 10 is a graphical flowchart describing a method of monitoring a weld signature. FIG.
  • DESCRIPTION OF THE PREFERRED EMBODIMENTS
  • With reference to the drawings, wherein in the various figures, like reference numerals correspond to like or similar components, and with 1 Starting here, an apparatus and method are provided for monitoring a weld signature of a welding process that may be used in a variety of different welding processes, operations on a single workpiece, assembly of two or more workpieces or surfaces, and / or assembly of two Ends of a single workpiece include, but are not limited to. Accordingly, a welding device comprises 10 an automatic or manual welding device or welding tongs 18 which comes with an integrated control unit or a controller 17 and a power supply 12 is functionally connected, which provides a voltage which in 1 as the variable "V" is shown. A variety of sensors 14 . 15 and 16 which may alternatively be configured as a single sensor and / or housed together in a common sensor housing (not shown) are for detecting, measuring, detecting and / or otherwise determining the values over time of one or more dynamically changing welding process variables which together define the "weld signature" as will be described in detail below.
  • The welding tongs 18 is configured to perform a welding operation such as, without limitation, gas metal arc welding (MIG) or tungsten inert gas (TIG) welding at one or more welds or welds on or along one or more workpieces 24 selectively executes. The welding tongs 18 can be on a manual or robotic arm 21 be mounted in an adjustable and reorientable manner, such as by selective tilting and / or turning. The welding device 10 includes at least one electrode 20A which, as shown, a portion of a nozzle of the welding gun 18 can be, and an electrode 20B , which is shown as a plate on which the workpiece 24 is positioned, the electrodes 20A . 20B are generally positioned opposite each other when the welding gun 18 is active or a high temperature arc 22 generated. The controller 17 contains a neural network 50 (see also 4 ), a training signature database 90 and a procedure 100 for adaptive welding monitoring or classification for use of the neural network 50 and the training signature database 90 for monitoring and eventual Classify a welding signature in real time during a welding process.
  • According to the invention, the method uses 100 the neural network 50 (see also 4 ) as an information processing paradigm capable of real time viewing and detecting, in real time, a total or combined set of detectable or measurable welding process variables, hereinafter referred to as the welding signature, of a particular pattern represented by the welding signature predetermined set of welding quality criteria acceptable, good or passed or unacceptable, poor or failed. The neural network 50 is initially trained during a controlled training process by the neural network 50 for example, to a plurality of training weld signatures, each of which conforms to an acceptable weld signature according to the predetermined set of weld quality criteria, as will be understood by those skilled in the art. The neural network 50 can also be continuously trained by the neural network 50 is exposed to additional acceptable weld signatures over time to improve the accuracy of pattern recognition and weld signature classification of the neural network 50 continue to develop and refine, as described below.
  • As those skilled in the art will understand, neural networks such as the neural network 50 may be used to predict a particular result and / or to recognize a pattern represented by suboptimal, inaccurate and / or relatively complex input data sets. Such a complex input data set may consist, for example, of the more typical welding process variables, ie the welding voltage V, the welding current i and the wire feeding speed (WFS) as described above, and / or other such dynamically changing input variables as described below with reference to FIG 4 is described.
  • Neural networks also serve to adapt or "learn" by repeatedly exposing them to different training sets, such as any monitored or unmonitored input data sets, and dynamically associate appropriate weightings and / or relative significance values with each of the various different subinformation items Form input data set. Neural networks are generally not preprogrammed to perform a particular task, as is the case with various control algorithms that use a preset maximum / minimum threshold limit for each individual value, without in any way predicting or classifying the entire or all monitored weld signature , Neural networks, such as the neural network 50 from 1 and 4 Instead, associative memory is used to represent the entirety or universe of the combined input sentence, such as the welding system input set "I", which in 4 to which the neural network is exposed to effectively generalize. In this way, a properly trained neural network may be able to accurately and consistently predict a future state from past experience, to classify a complex dataset as needed, as indicated by the arrow O in FIG 4 and / or to recognize an overall pattern represented by the entirety of the complex data set, which otherwise may require significant time and / or experience for correct deciphering.
  • Regarding 2 For example, such a complex input data set described above may be referred to herein as a weld signature 30 be executed. The sweat signature 30 , what a 2 represents a typical, good, or otherwise acceptable weld signature, ie, a weld signature that has been somehow validated to produce a resulting weld (not shown), the predetermined subjective and / or objective criteria of strength, quality, uniformity and / or other such criteria. The sweat signature 30 itself represents the values of at least three different variables over a period of time, ie the wire feed rate (WFS), the welding voltage V and the welding current i, each of which has a corresponding track, as in FIG 2 is shown. That is, the track 32 the wire feed rate (WFS) as described above, which is near the welding gun 18 (please refer 1 ) using the sensor 16 (please refer 1 ) can be measured or detected. The track 34 sets the welding current i at or near the welding gun 18 as he passes through the sensor 15 (please refer 1 ), the fluctuations in the welding current (lane 34 ) correlate with any variations in wire feed rate (WFS), as understood by those skilled in the art. The track 36 Sets the measured voltage at or near the welding gun 18 using the sensor 14 (please refer 1 ).
  • Regarding 3 is a representative failed or otherwise unacceptable weld signature 30A that is, a weld signature that generates a weld (not shown) that does not meet predetermined subjective and / or objective strength, quality, uniformity, or other criteria. The sweat signature 30A contains the values of the same three individual variables over time described above, ie the wire feed rate (WFS), the voltage and the current. The track 32A represents the wire feed rate (WFS) as described above. The track 34A represents the measured current, whereby the fluctuations in the current (lane 34A ) correlate with any variations in wire feed rate (WFS), as understood by those skilled in the art. Likewise, the track represents 36A the measured stress at or near the welding gun 18 using the sensor 14 (please refer 1 ).
  • The welding signatures 30 . 30A of the 2 respectively. 3 are representative of the actual welding signatures required to fill a given training signature database 90 (please refer 1 ) may vary depending on the welding process and the weld quality criteria.
  • Regarding 4 is the above-described neural network 50 in the controller 17 (please refer 1 ), stored therein, or otherwise accessible to it, and may be processed by the algorithm 100 (please refer 1 and 5 ) can be used to accurately predict, classify, or otherwise recognize a pattern in a current weld signature. The neural network 50 includes at least one input layer 40 with a variety of different input neurons or input nodes 41 each of which is configured to receive data, measurements and / or other predetermined information from outside the neural network 50 receive. As in 4 In one embodiment, this information or input sentence I includes the welding voltage V, the welding current I, the wire feeding speed or WFS, all of which are also shown in FIG 1 are shown but are not limited thereto. At least one additional input node 41 may be configured to receive additional part input data, a measurement, or other process information as needed, as represented by the variable X. For example, the input variable X may correspond to a specific arc protective gas composition used in an arc welding process.
  • The neural network 50 further comprises at least one "hidden" layer 42 containing a multitude of hidden neurons or hidden nodes 43 each of which receives and forwards information from the input nodes 41 the input layer 40 is output, with the hidden nodes 43 the processed information to other neurons or nodes of one or more additional hidden layers (not shown), if used, or directly to an output layer 44 hand off. The starting layer 44 also contains at least one output neuron or one parent node 45 , the information or the information outside the neural network 50 forwards or transmits, such as to the display device 11 (please refer 1 ) and / or the training database 90 (please refer 1 ) as by the algorithm 100 which is described below with reference to 5 is described.
  • In the representative embodiment of 4 can be any of the neurons or each of the nodes 43 . 45 the hidden layer 42 or the starting layer 44 as shown may use a tan-sigmoidal (or tan-S-shaped) transfer or activation function, but it may alternatively have a linear activation function and / or other types of S-shaped or other activation functions and / or different numbers of hidden layers, as desired 42 and / or nodes 43 . 44 use to achieve the desired level of predictive accuracy, depending on the particular output required (arrow O). In one embodiment, the neural network becomes 50 initially trained using the well-known Levenberg-Marquardt back propagation algorithm, but training is not so limited since any other suitable training method or algorithm may be used with the invention.
  • Regarding 5 can the inventive method 100 (see also 1 ) in the controller 17 (please refer 1 ), stored, recorded, or otherwise executable by it, and begins to step 102 at. The step 102 includes at least one preliminary training process, as the term is understood by those skilled in the art, wherein the neural network 50 from 4 is trained to accurately recognize a passed, good, or otherwise acceptable sweat signature. An acceptable weld signature may be any weld signature that corresponds to a validated weld, ie, a weld that meets a predetermined set of criteria for quality, strength, uniformity, and / or other desirable properties or qualities, as described above. The step 102 can be performed by the neural network 50 from 4 a number of sufficiently different or varied acceptable weld signatures, such as in FIG 2 represented, exposed or subjected. The greater the number of training data sets presented to a neural network, and the greater the deviation of these data sets from each other, the more accurate is the classification or pattern recognition by and / or the neural network prediction value. After one correct training of the neural network 50 this is how the procedure works 100 to step 104 further.
  • At step 104 measures, detects or determines the process 100 otherwise values for each of the variables which the input data set I of 4 includes, such as but not limited to welding voltage V, welding current i and wire feeding speed (WFS), and a variable X (see FIG 4 ), such as a special blanket gas composition, and then continuously monitors these values for the time it takes to complete a single weld. The values at step 104 can be done using the sensors 14 . 15 and 16 from 1 be determined. Once these values are in step 104 were correctly determined, the procedure goes 100 to step 106 further.
  • At step 106 is the input data seat I (see 4 ) of step 104 the input layer 40 of the neural network 50 as well as in 4 is shown, supplied or directed to this. The neural network 50 then dynamically assigns weights to the various variables making up the input record I, and pulls any associated data matrices and / or training records of the training database 90 (please refer 1 ) approached by the neural network 50 can be used to thereby reduce the current welding signal generated in 5 for the sake of simplicity, is abbreviated as WS. The procedure 100 then go to step 108 further.
  • At step 108 classifies the neural network 50 the welding signal (WS) into one of a number of different welding categories or classifications. For example, the output (the arrow O of 4 ) from the starting layer 44 of the neural network 50 , this in 4 is normalized, ie, assigned a value between -1 and 1, such as using a tan-sigmoidal or other transfer function or activation function at the output node 45 (please refer 4 ) as described above. Values that fall in the range between -1 and 0 may be selected to correspond to an unacceptable or failed weld signature, while values falling within the range between 0 and 1 may be classified as an acceptable or passed weld signature can.
  • Within these respective classifications, whose corresponding normalized values may be changed as desired in accordance with operator preferences, a normalized value that approximates a minimum value, ie, -1, may be considered less desirable than, for example, a weld signature that is a normalized one Value of -0.1, while a normalized value which approximates that of FIG. 1 may be classified as more desirable or more acceptable than e.g. B. is a welding signature, which has a normalized value of 0.1. Similarly, a value of 0 may indicate a weld signature corresponding to the neural network 50 (please refer 4 ) is acceptable and unacceptable at the same time, possibly requiring further investigation, testing, weld validation and / or other analysis for proper classification. After classifying the welding signature (WS), the procedure goes 100 then continue to step 110 ,
  • At step 110 determines the procedure 100 whether at step 108 classified welding signature (WS) is equal to a first category or classification representing an acceptable welding signature, this classification being in 5 for the sake of simplicity, is abbreviated as C1. If the classification of the welding signature (WS) falls into the classification C1, the procedure goes 100 to step 112 Continue, the procedure 100 otherwise go to step 114 continues.
  • At step 112 can the procedure 100 a flag or other appropriate flag in the controller 17 (please refer 1 ) equals an integer value that corresponds to or identifies the classification, such as 1, or any other value that corresponds to a positive or a passed classification, as in step 110 was determined. The procedure 100 then go to the steps 116 and 118 further.
  • At step 114 sets the procedure 100 after step by step 110 it has been determined that the classification of the welding signature (WS) is not equal to the value determined at step 112 has been assigned, for. 1, a flag or other marker in the controller 17 (please refer 1 ) is equal to 0, or to any other value corresponding to a negative or failed classification as determined at step 110 was determined. The procedure 100 then go on to the steps 115 and 116 ,
  • After at step 114 A flag is set indicating a negative, unacceptable, or otherwise failed current weld signature (WS0) records the process 100 at step 115 the weld signature (WS0) for possible future use as a training set in the controller 17 temporarily on. The procedure 100 then go to step 117 further.
  • At step 116 can the procedure 100 a notification device 11 (please refer 1 ) selectively activate an operator via the Classification of the sweat signature (WS) passing through the neural network 50 (please refer 4 ), to inform visually or acoustically, such as by a notification device 11 (please refer 1 ) is activated near the operator. For example, when a normalized value of a classification falls in the range between -1 and 0, the notification device may 11 illuminate in a color such as red, indicating an unacceptable sweat signature (WS0), and / or sound an easily identifiable audible alarm.
  • Similarly, the notification device 11 in a different color, such as green, when a normalized value of the classification falls within a predetermined range, such as between 1 and 0.5, or any other predetermined range corresponding to a welding signature (WS) different from the neural network 50 (please refer 4 ) is predicted to have a particularly high probability of having high strength / quality of the weld. Normalized values falling within a further predetermined range, such as between 0 and 0.5, may illuminate in yet another color, such as yellow or orange, indicating that the classified weld signature (WS) is approaching an unacceptable level can, which requires further process control and / or analysis. It can be expected that an operator who is notified of a weld signature will be aware of the neural network 30 (please refer 1 ) is detected as failed, takes an immediate action to stop and / or take a corrective action, so that the procedure 100 at step 116 can end if a weld signature is classified as unacceptable.
  • At step 117 the process correlates 100 the temporarily stored unacceptable weld signature (WS0) with a weld dataset to determine if the weld signature (WS) has been correctly classified. For example, a weld (not shown) may be selected and destructively tested to determine if the weld lacks the required strength, uniformity, and / or other desired properties, such as through the neural network 50 (please refer 4 ) was predicted to be unacceptable or failed when classifying the weld signature (WS0). Alternatively or in parallel, the method 100 the instantaneous weld signature (WS0) correlates with each of the weld signatures in the training signature database 90 (please refer 1 ) and determine whether the weld signature (WS0) previously classified as unacceptable differs sufficiently from each of the weld signatures in the training database 90 from 1 are included. The procedure 100 then go on to step 122 ,
  • After at step 112 a flag is set to 1 indicating a positive or passed sweat rating, records the procedure 100 at step 118 the weld signature (WS1) in the controller 17 temporarily for a potential future use as a training set. The procedure 100 then go on to step 120 ,
  • At step 120 the process correlates 100 the temporarily stored weld signature (WS1) with a weld dataset to determine if the weld signature (WS1) has been correctly classified. For example, a weld (not shown) may be selected and destructively tested to determine if the weld has the required strength, uniformity, and / or other desired properties, such as through the neural network 50 (please refer 4 ) was predicted when classifying the acceptable weld signature (WS1). Alternatively or in parallel, the method 100 the weld signature (WS1) correlate with each of the weld signatures in the training signature database 90 (please refer 1 ) and determine whether the weld signature (WS) previously classified as acceptable differs sufficiently from each of the weld signatures in the training signature database 90 from 1 are included. The procedure 100 then go to step 122 further.
  • At step 122 determines the procedure 100 whether at step 118 recorded acceptable weld signature (WS1) in light of the results of step 120 should be maintained. When the sweat signature (WS1) of each of the in the training signature database 90 (please refer 1 ) is sufficiently different, the method determines 100 in that the weld signature (WS1) has enough value as a training sweat signature to be added to the training signature database 90 (please refer 1 ) to justify. The procedure 100 jump again to step 102 and continues the neural network 50 from 4 to train by doing the neural network 50 the weld signature (WS1), which occurs at step 118 was recorded, making the weld signature (WS1) to the training signature database 90 (please refer 1 ) will be added. Otherwise, the procedure goes 100 to step 124 further.
  • At step 124 clears the procedure 100 the welding signature (WS1), which is shown at step 118 was recorded temporarily and repeats the step 104 as described above.
  • Although the best modes for carrying out the invention have been described in detail, those familiar with the art to which this invention relates will recognize various alternative designs and embodiments for practicing the invention within the scope of the appended claims.

Claims (2)

  1. Procedure ( 100 ) for monitoring a welding signature ( 30 . 30A ) during an arc welding process, comprising: determining a plurality of different welding process variables (V, i, WFS) representing the welding signature ( 30 . 30A defining at least one welding voltage (V), a welding current (i) and a wire feeding speed (WFS); and the welding signature ( 30 . 30A ) using a neural network ( 50 ) is classified into one of a plurality of different sweat classifications, the neural network ( 50 ) a plurality of input nodes ( 40 ) each of which corresponds to another of the plurality of different welding process variables (V, i, WFS); wherein the classification of the welding signature ( 30 . 30A ) is characterized by the absence of a comparison of any one of the plurality of different welding process variables (V, i, WFS) with a corresponding threshold; the method further comprising: the welding signature ( 30 . 30A ) with a database ( 90 ) of training welding signatures after the welding signature ( 30 . 30A ) is classified; It is determined whether the welding signature ( 30 . 30A ) of each of the training weld signatures in the database ( 90 ) sufficiently differentiates; the welding signature ( 30 . 30A ) in the database ( 90 ) is detected when it is determined that the weld signature ( 30 . 30A ) differs sufficiently from each of the training weld signatures; a weld is tested after classification to thereby determine a weld dataset containing the values of each of a plurality of different weld characteristics; and the welding signature ( 30 . 30A ) is correlated with the welding data set to thereby enable the database ( 90 ) to validate.
  2. Procedure ( 100 ) according to claim 1, further comprising: a notification device ( 11 ) is activated in a manner when the welding signature ( 30 . 30A ) is classified as a first of the different sweat classifications, and in another way if the sweat signature is ( 30 . 30A ) is classified as a second of the different sweat classifications.
DE102009007514A 2008-02-08 2009-02-05 Method and apparatus for monitoring a weld signature Active DE102009007514B4 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US12/028,431 2008-02-08
US12/028,431 US20090200282A1 (en) 2008-02-08 2008-02-08 Weld signature monitoring method and apparatus

Publications (2)

Publication Number Publication Date
DE102009007514A1 DE102009007514A1 (en) 2009-09-03
DE102009007514B4 true DE102009007514B4 (en) 2012-01-05

Family

ID=40911504

Family Applications (1)

Application Number Title Priority Date Filing Date
DE102009007514A Active DE102009007514B4 (en) 2008-02-08 2009-02-05 Method and apparatus for monitoring a weld signature

Country Status (3)

Country Link
US (1) US20090200282A1 (en)
CN (1) CN101502906B (en)
DE (1) DE102009007514B4 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102015221588A1 (en) * 2015-11-04 2017-05-04 Robert Bosch Gmbh Welding control for welding device and welding process for manufacturing plant

Families Citing this family (70)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9104195B2 (en) 2006-12-20 2015-08-11 Lincoln Global, Inc. Welding job sequencer
US9352411B2 (en) 2008-05-28 2016-05-31 Illinois Tool Works Inc. Welding training system
US8834168B2 (en) 2008-08-21 2014-09-16 Lincoln Global, Inc. System and method providing combined virtual reality arc welding and three-dimensional (3D) viewing
US8747116B2 (en) 2008-08-21 2014-06-10 Lincoln Global, Inc. System and method providing arc welding training in a real-time simulated virtual reality environment using real-time weld puddle feedback
US9011154B2 (en) 2009-07-10 2015-04-21 Lincoln Global, Inc. Virtual welding system
US9196169B2 (en) 2008-08-21 2015-11-24 Lincoln Global, Inc. Importing and analyzing external data using a virtual reality welding system
US9483959B2 (en) 2008-08-21 2016-11-01 Lincoln Global, Inc. Welding simulator
US9330575B2 (en) 2008-08-21 2016-05-03 Lincoln Global, Inc. Tablet-based welding simulator
US9280913B2 (en) 2009-07-10 2016-03-08 Lincoln Global, Inc. Systems and methods providing enhanced education and training in a virtual reality environment
US8851896B2 (en) 2008-08-21 2014-10-07 Lincoln Global, Inc. Virtual reality GTAW and pipe welding simulator and setup
US9318026B2 (en) 2008-08-21 2016-04-19 Lincoln Global, Inc. Systems and methods providing an enhanced user experience in a real-time simulated virtual reality welding environment
US8911237B2 (en) 2008-08-21 2014-12-16 Lincoln Global, Inc. Virtual reality pipe welding simulator and setup
US7873495B2 (en) * 2009-02-24 2011-01-18 Inspectech Corporation Welding quality control and monitoring system
US8274013B2 (en) 2009-03-09 2012-09-25 Lincoln Global, Inc. System for tracking and analyzing welding activity
CN106233358A (en) 2014-06-02 2016-12-14 林肯环球股份有限公司 System and method for artificial welders training
US9230449B2 (en) 2009-07-08 2016-01-05 Lincoln Global, Inc. Welding training system
US20160093233A1 (en) 2012-07-06 2016-03-31 Lincoln Global, Inc. System for characterizing manual welding operations on pipe and other curved structures
US9221117B2 (en) 2009-07-08 2015-12-29 Lincoln Global, Inc. System for characterizing manual welding operations
US9773429B2 (en) 2009-07-08 2017-09-26 Lincoln Global, Inc. System and method for manual welder training
US8569655B2 (en) 2009-10-13 2013-10-29 Lincoln Global, Inc. Welding helmet with integral user interface
US8884177B2 (en) 2009-11-13 2014-11-11 Lincoln Global, Inc. Systems, methods, and apparatuses for monitoring weld quality
US9468988B2 (en) 2009-11-13 2016-10-18 Lincoln Global, Inc. Systems, methods, and apparatuses for monitoring weld quality
US8569646B2 (en) 2009-11-13 2013-10-29 Lincoln Global, Inc. Systems, methods, and apparatuses for monitoring weld quality
US8742280B2 (en) * 2010-01-07 2014-06-03 Illinois Tool Works Inc. Systems and methods for statistically analyzing welding operations
US8762520B2 (en) 2010-07-02 2014-06-24 At&T Intellectual Property I, L.P. Method and system to detect a predictive network signature
JP6211243B2 (en) * 2011-06-29 2017-10-11 株式会社ダイヘン Arc welding monitor
US9101994B2 (en) 2011-08-10 2015-08-11 Illinois Tool Works Inc. System and device for welding training
US9573215B2 (en) 2012-02-10 2017-02-21 Illinois Tool Works Inc. Sound-based weld travel speed sensing system and method
US9767712B2 (en) 2012-07-10 2017-09-19 Lincoln Global, Inc. Virtual reality pipe welding simulator and setup
US9583014B2 (en) 2012-11-09 2017-02-28 Illinois Tool Works Inc. System and device for welding training
US9368045B2 (en) 2012-11-09 2016-06-14 Illinois Tool Works Inc. System and device for welding training
FI124470B (en) * 2013-01-29 2014-09-15 Kemppi Oy Improved control unit for a welding device
US9728103B2 (en) 2013-03-15 2017-08-08 Illinois Tool Works Inc. Data storage and analysis for a welding training system
US9583023B2 (en) 2013-03-15 2017-02-28 Illinois Tool Works Inc. Welding torch for a welding training system
US9713852B2 (en) 2013-03-15 2017-07-25 Illinois Tool Works Inc. Welding training systems and devices
US9666100B2 (en) 2013-03-15 2017-05-30 Illinois Tool Works Inc. Calibration devices for a welding training system
US9672757B2 (en) 2013-03-15 2017-06-06 Illinois Tool Works Inc. Multi-mode software and method for a welding training system
US20140346158A1 (en) 2013-05-24 2014-11-27 Lincoln Global, Inc. Systems and methods providing a computerized eyewear device to aid in welding
US20150072323A1 (en) 2013-09-11 2015-03-12 Lincoln Global, Inc. Learning management system for a real-time simulated virtual reality welding training environment
US10083627B2 (en) 2013-11-05 2018-09-25 Lincoln Global, Inc. Virtual reality and real welding training system and method
CN103551709B (en) * 2013-11-16 2015-04-22 沈阳工业大学 Welding joint forming detection device and method for A-TIG welding
US10056010B2 (en) 2013-12-03 2018-08-21 Illinois Tool Works Inc. Systems and methods for a weld training system
US9724788B2 (en) 2014-01-07 2017-08-08 Illinois Tool Works Inc. Electrical assemblies for a welding system
US9751149B2 (en) 2014-01-07 2017-09-05 Illinois Tool Works Inc. Welding stand for a welding system
US9589481B2 (en) 2014-01-07 2017-03-07 Illinois Tool Works Inc. Welding software for detection and control of devices and for analysis of data
US10105782B2 (en) 2014-01-07 2018-10-23 Illinois Tool Works Inc. Feedback from a welding torch of a welding system
US10170019B2 (en) 2014-01-07 2019-01-01 Illinois Tool Works Inc. Feedback from a welding torch of a welding system
US9757819B2 (en) 2014-01-07 2017-09-12 Illinois Tool Works Inc. Calibration tool and method for a welding system
US9836987B2 (en) 2014-02-14 2017-12-05 Lincoln Global, Inc. Virtual reality pipe welding simulator and setup
US10307853B2 (en) 2014-06-27 2019-06-04 Illinois Tool Works Inc. System and method for managing welding data
US10665128B2 (en) 2014-06-27 2020-05-26 Illinois Tool Works Inc. System and method of monitoring welding information
US9937578B2 (en) 2014-06-27 2018-04-10 Illinois Tool Works Inc. System and method for remote welding training
US9862049B2 (en) 2014-06-27 2018-01-09 Illinois Tool Works Inc. System and method of welding system operator identification
US9724787B2 (en) 2014-08-07 2017-08-08 Illinois Tool Works Inc. System and method of monitoring a welding environment
US9875665B2 (en) 2014-08-18 2018-01-23 Illinois Tool Works Inc. Weld training system and method
US10239147B2 (en) 2014-10-16 2019-03-26 Illinois Tool Works Inc. Sensor-based power controls for a welding system
US10402959B2 (en) 2014-11-05 2019-09-03 Illinois Tool Works Inc. System and method of active torch marker control
US10417934B2 (en) 2014-11-05 2019-09-17 Illinois Tool Works Inc. System and method of reviewing weld data
US10204406B2 (en) 2014-11-05 2019-02-12 Illinois Tool Works Inc. System and method of controlling welding system camera exposure and marker illumination
US10373304B2 (en) 2014-11-05 2019-08-06 Illinois Tool Works Inc. System and method of arranging welding device markers
US10490098B2 (en) 2014-11-05 2019-11-26 Illinois Tool Works Inc. System and method of recording multi-run data
US10210773B2 (en) 2014-11-05 2019-02-19 Illinois Tool Works Inc. System and method for welding torch display
US10427239B2 (en) 2015-04-02 2019-10-01 Illinois Tool Works Inc. Systems and methods for tracking weld training arc parameters
US10593230B2 (en) 2015-08-12 2020-03-17 Illinois Tool Works Inc. Stick welding electrode holder systems and methods
US10657839B2 (en) 2015-08-12 2020-05-19 Illinois Tool Works Inc. Stick welding electrode holders with real-time feedback features
US10373517B2 (en) 2015-08-12 2019-08-06 Illinois Tool Works Inc. Simulation stick welding electrode holder systems and methods
US10438505B2 (en) 2015-08-12 2019-10-08 Illinois Tool Works Welding training system interface
CN105081524B (en) * 2015-08-27 2016-09-28 清华大学 In welding process, the online dynamic programming of track follows the tracks of collaborative control method with welding bead
EP3319066A1 (en) 2016-11-04 2018-05-09 Lincoln Global, Inc. Magnetic frequency selection for electromagnetic position tracking
US20180361514A1 (en) * 2017-06-20 2018-12-20 Lincoln Global, Inc. Machine learning for weldment classification and correlation

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE4112985C2 (en) * 1991-04-20 1995-08-31 Juergen Dipl Ing Borowka Method and device for automatically guiding a welding head
DE19518804A1 (en) * 1994-05-27 1995-12-21 Fraunhofer Ges Forschung Process control
DE19957163C1 (en) * 1999-11-27 2001-08-09 Thyssenkrupp Stahl Ag Method and device for quality control of the seam on sheets or strips butt welded with a laser

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5278390A (en) * 1993-03-18 1994-01-11 The Lincoln Electric Company System and method for controlling a welding process for an arc welder
JP2001276980A (en) * 2000-03-30 2001-10-09 Matsushita Electric Ind Co Ltd Connecting apparatus
US6441342B1 (en) * 2000-11-20 2002-08-27 Lincoln Global, Inc. Monitor for electric arc welder
US6857553B1 (en) * 2002-04-17 2005-02-22 The United States Of America As Represented By The United States Department Of Energy Method and apparatus for in-process sensing of manufacturing quality
CN1220034C (en) * 2003-07-23 2005-09-21 天津大学 Method for determining fusion mugget area of resistance spot welding for allautal through technique of syncretizing multiple informations
CN1546268A (en) * 2003-12-17 2004-11-17 南昌大学 Intelligent control system for weld seam tracking and fusion penetration in spiral pipes
US8431862B2 (en) * 2005-08-25 2013-04-30 Lincoln Global, Inc. Torch for electric arc welding system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE4112985C2 (en) * 1991-04-20 1995-08-31 Juergen Dipl Ing Borowka Method and device for automatically guiding a welding head
DE19518804A1 (en) * 1994-05-27 1995-12-21 Fraunhofer Ges Forschung Process control
DE19957163C1 (en) * 1999-11-27 2001-08-09 Thyssenkrupp Stahl Ag Method and device for quality control of the seam on sheets or strips butt welded with a laser

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102015221588A1 (en) * 2015-11-04 2017-05-04 Robert Bosch Gmbh Welding control for welding device and welding process for manufacturing plant

Also Published As

Publication number Publication date
DE102009007514A1 (en) 2009-09-03
CN101502906A (en) 2009-08-12
CN101502906B (en) 2013-05-22
US20090200282A1 (en) 2009-08-13

Similar Documents

Publication Publication Date Title
US9764408B2 (en) Devices and methods for analyzing spatter generating events
US10239158B2 (en) Laser hybrid welding control systems and methods
US8987628B2 (en) Systems, methods, and apparatuses for monitoring weld quality
ES2336481T3 (en) Welding procedure and welding system with determination of the position of blowing to weld.
US5717187A (en) Plasma torch condition monitoring
EP1238744B1 (en) Laser weld quality monitoring method and system
WO2017019860A1 (en) System and method to facilitate welding software as a service
EP1624993B1 (en) System and method for self-adaptive on-line control of a flash-butt-welding machine
EP1618984B1 (en) Laser welding process and device
CA2004311C (en) Arrangement for monitoring the quality of electric welds
US20160346861A1 (en) Automatic Weld Arc Monitoring System
JP5133490B2 (en) Spot welding apparatus and method for detecting welding conditions in real time
CA2359424C (en) Monitor for electric arc welder
EP2022592B1 (en) Method, device and system for determining welding speed for a manual arc welding process
US4375026A (en) Weld quality monitor
JP5583821B2 (en) Ultrasonic bonding method and bonding apparatus
US20050127052A1 (en) Near real time arc welding monitor
EP0655294B1 (en) Process for simultaneously measuring temperatures in a laser seam welding using at least two pyrometers and process parameters treatment and seam quality control
US8592719B2 (en) System and method for identifying welding consumable wear
DE212014000102U1 (en) Systems for providing contact point-to-workpiece distance (CTWD) augmented reality feedback
US20040034608A1 (en) Luminescence sensing system for welding
US8847100B2 (en) Weld cap and tip inspection method and apparatus
CN106964874B (en) System and method for monitoring welding quality
DE69821791T3 (en) Device for monitoring arc welding
Pal et al. Artificial neural network modeling of weld joint strength prediction of a pulsed metal inert gas welding process using arc signals

Legal Events

Date Code Title Description
OP8 Request for examination as to paragraph 44 patent law
8180 Miscellaneous part 1

Free format text: PFANDRECHT

R081 Change of applicant/patentee

Owner name: GM GLOBAL TECHNOLOGY OPERATIONS LLC (N. D. GES, US

Free format text: FORMER OWNER: GM GLOBAL TECHNOLOGY OPERATIONS, INC., DETROIT, MICH., US

Effective date: 20110323

Owner name: GM GLOBAL TECHNOLOGY OPERATIONS LLC (N. D. GES, US

Free format text: FORMER OWNER: GM GLOBAL TECHNOLOGY OPERATIONS, INC., DETROIT, US

Effective date: 20110323

8127 New person/name/address of the applicant

Owner name: GM GLOBAL TECHNOLOGY OPERATIONS LLC , ( N. D. , US

R018 Grant decision by examination section/examining division
R020 Patent grant now final

Effective date: 20120406